[BUG] dealing with sklearn 1.2 deprecation warnings

[fkiraly]

A number of sklearn calls raise deprecation warnings and will turn into bugs when sklearn releases version 1.2.
These should be fixed.

• replacing float variable names by str in pandas.DataFrame passed:

classification/feature_based/_summary_classifier.py: 2 warnings
classification/feature_based/tests/test_summary_classifier.py: 2 warnings
classification/tests/test_all_classifiers.py: 6 warnings
tests/test_all_estimators.py: 23 warnings
  C:\Miniconda\envs\test\lib\site-packages\sklearn\utils\validation.py:1692: FutureWarning: Feature names only support names that are all strings. Got feature names with dtypes: ['float', 'str']. An error will be raised in 1.2.

• replacing normalize by use of StandardScaler:

transformations/panel/rocket/tests/test_MiniRocket.py::test_minirocket_on_gunpoint
transformations/panel/rocket/tests/test_MiniRocketMultivariate.py::test_minirocket_multivariate_on_basic_motions
transformations/panel/rocket/tests/test_MultiRocket.py::test_multirocket_on_gunpoint
transformations/panel/rocket/tests/test_MultiRocketMultivariate.py::test_multirocket_multivariate_on_basic_motions
transformations/panel/rocket/tests/test_Rocket.py::test_rocket_on_gunpoint
  C:\Miniconda\envs\test\lib\site-packages\sklearn\linear_model\_base.py:145: FutureWarning: 'normalize' was deprecated in version 1.0 and will be removed in 1.2.
  If you wish to scale the data, use Pipeline with a StandardScaler in a preprocessing stage. To reproduce the previous behavior:
  
  from sklearn.pipeline import make_pipeline
  
  model = make_pipeline(StandardScaler(with_mean=False), _RidgeGCV())

[KishenSharma6]

Hi @fkiraly , I'd like to work on this bug.

[fkiraly]

alright, @KishenSharma6, thanks! Pick one of the two to start with, I suggest.

[KishenSharma6]

Thanks @fkiraly , the pr #2167 is for replacing normalize by use of StandardScaler.

Please let me know if that pr needs anything additional, I will begin on replacing float variable names by str in pandas.DataFrame passed:

[hmtbgc]

@KishenSharma6 I am sorry that I have PR the first part. You have done a good job. Thanks for your contribution!

[KishenSharma6]

@hmtbgc no worries, thank you so much! I'm having issues building sktime from source so your assistance was much needed and greatly appreciated :)

[jaivanti]

Hi! I would like to work on this?

[jaivanti]

If possible can you please brief more about the the 1st part....Like as a beginner just want to clarify more on it. Thanks

[KishenSharma6]

@fkiraly We can mark this one as completed. PR #2167 and #2190 for reference

@jaivanti sorry for the late reply, we were able to complete this one. Feel free to work on another issue. You can reference #2190 to see how @hmtbgc solved the issue (namely changing input data types).

[fkiraly]

Yes, indeed, @KishenSharma6, this is done. Forgot to update and close after #2190, thanks for pointing this out!